Region Measure

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does so well: it discloses the measurement basis (mean power per STFT cell, 1024-point window, 64-sample hop at 44.1 kHz), the reference-band default (whole spectrum), and the normalization needed for cross-clip comparison. It omits any statement about cost, output shape, or what happens with no source given, but the safety-relevant behavior of a measurement tool is adequately conveyed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core definition, then use cases, then methodology, then comparison advice — a sensible order. Slightly dense with parentheticals (STFT details, de-bias references), but every sentence contributes information an agent would otherwise lack.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists, so return values need not be explained, and the description covers the measurement domain, default reference band, and cross-clip comparison protocol. The main gap is that several schema parameters (bars, source, project) receive no explanation despite 0% schema coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% for 9 parameters, so the description must compensate. It does explain the core measurement parameters well — seconds as [t0, t1], f_lo..f_hi, the reference band defaulting to the whole spectrum, and level_lufs=-25 for comparison — but leaves bars, source, and project completely undocumented, so several parameters remain opaque.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Power in a zoom box… in dB') and adds the reference-band comparison, which distinguishes it from plain spectral measurement siblings like sound_zoom or cmp_zoom. The measurement domain (power, not mean dB) is called out so the agent knows exactly what quantity this returns.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to reach for it ('one word's hiss, one band in one moment… whether a fix moved a box by the dB you meant') and gives a concrete comparison procedure (same box, level_lufs=-25). It names sound_zoom_diff as the related tool but does not state a clear exclusion case for when NOT to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.